© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 31397
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals or names in the context of art or culture

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mate
    -0.07
    ģ
    -0.07
    ourage
    -0.07
    ÑĤаÑĢ
    -0.07
    -share
    -0.07
    915
    -0.06
    stead
    -0.06
    avana
    -0.06
    side
    -0.06
    208
    -0.06
    POSITIVE LOGITS
    osate
    0.07
    oves
    0.07
    enheim
    0.07
    itis
    0.07
    bum
    0.07
    OUND
    0.07
    ral
    0.07
    æ³Ľ
    0.07
    anut
    0.07
    ÑģÑĮ
    0.07
    Activations Density 0.031%

    No Known Activations